公开(公告)号：US07599519B2

公开(公告)日：2009-10-06

申请号：US11200148

申请日：2005-08-10

申请人： Kouji Yokouchi ,  Sadato Akahori ,  Kensuke Terakawa

发明人： Kouji Yokouchi ,  Sadato Akahori ,  Kensuke Terakawa

IPC分类号： G06K9/00 ,  H04N5/222

CPC分类号： G06K9/00248 ,  G06K9/0061 ,  G06T5/005 ,  G06T5/20 ,  G06T7/12 ,  G06T7/90 ,  G06T2207/10024 ,  G06T2207/20064 ,  G06T2207/20132 ,  G06T2207/30216 ,  H04N1/624

摘要： Structural element candidates, estimated to be predetermined structural elements of a predetermined subject, are detected from an image that includes the subject. The subject that includes the structural element candidates is detected from the image in the vicinity of the detected structural element candidates. The characteristics of the structural elements are discriminated from the image in the vicinity of the structural element candidates, at a higher accuracy than when the structural elements were detected. In the case that the characteristics of the structural elements are discriminated, the structural element candidates are confirmed as being the predetermined structural elements.

摘要翻译： 估计为预定对象的预定结构元素的结构元素候选被从包括对象的图像中检测出。 从检测到的结构要素候补附近的图像中检测出包含结构要素候选的被摄体。 结构元件的特性与结构元件候选物附近的图像相比，比检测到结构元件时的精度更高。 在鉴别结构要素的特征的情况下，将结构要素作为规定的结构要素。

公开(公告)号：US20060035259A1

公开(公告)日：2006-02-16

申请号：US11200148

申请日：2005-08-10

申请人： Kouji Yokouchi ,  Sadato Akahori ,  Kensuke Terakawa

发明人： Kouji Yokouchi ,  Sadato Akahori ,  Kensuke Terakawa

IPC分类号： C12Q1/68 ,  G06F19/00 ,  G01N33/48 ,  G01N33/50

CPC分类号： G06K9/00248 ,  G06K9/0061 ,  G06T5/005 ,  G06T5/20 ,  G06T7/12 ,  G06T7/90 ,  G06T2207/10024 ,  G06T2207/20064 ,  G06T2207/20132 ,  G06T2207/30216 ,  H04N1/624

摘要： Structural element candidates, estimated to be predetermined structural elements of a predetermined subject, are detected from an image that includes the subject. The subject that includes the structural element candidates is detected from the image in the vicinity of the detected structural element candidates. The characteristics of the structural elements are discriminated from the image in the vicinity of the structural element candidates, at a higher accuracy than when the structural elements were detected. In the case that the characteristics of the structural elements are discriminated, the structural element candidates are confirmed as being the predetermined structural elements.

公开(公告)号：US08254644B2

公开(公告)日：2012-08-28

申请号：US12278616

申请日：2007-02-07

申请人： Yuanzhong Li ,  Sadato Akahori ,  Kensuke Terakawa ,  Yoshiro Kitamura ,  Wataru Ito

发明人： Yuanzhong Li ,  Sadato Akahori ,  Kensuke Terakawa ,  Yoshiro Kitamura ,  Wataru Ito

IPC分类号： G06K9/00 ,  G06K9/46

CPC分类号： G06K9/00281

摘要： First, a face within an image, which is a target of detection, is detected. Detection data of the face is employed to detect eyes which are included in the face. Detection data of the eyes are employed to detect the inner and outer corners of the eyes. Detection data of the inner and outer corners of the eyes is employed to detect characteristic points of the upper and lower eyelids that represent the outline of the eyes.

摘要翻译： 首先，检测作为检测对象的图像内的面部。 使用脸部的检测数据来检测包含在脸部中的眼睛。 眼睛的检测数据用于检测眼睛的内角和外角。 使用眼睛内外角的检测数据来检测表示眼睛轮廓的上眼睑和下眼睑的特征点。

公开(公告)号：US20090010544A1

公开(公告)日：2009-01-08

申请号：US12278616

申请日：2007-02-07

申请人： Yuanzhong Li ,  Sadato Akahori ,  Kensuke Terakawa ,  Yoshiro Kitamura ,  Wataru Ito

发明人： Yuanzhong Li ,  Sadato Akahori ,  Kensuke Terakawa ,  Yoshiro Kitamura ,  Wataru Ito

IPC分类号： G06K9/46

CPC分类号： G06K9/00281

摘要： First, a face within an image, which is a target of detection, is detected. Detection data of the face is employed to detect eyes which are included in the face. Detection data of the eyes are employed to detect the inner and outer corners of the eyes. Detection data of the inner and outer corners of the eyes is employed to detect characteristic points of the upper and lower eyelids that represent the outline of the eyes.

摘要翻译： 首先，检测作为检测对象的图像内的面部。 使用脸部的检测数据来检测包含在脸部中的眼睛。 眼睛的检测数据用于检测眼睛的内角和外角。 使用眼睛内外角的检测数据来检测表示眼睛轮廓的上眼睑和下眼睑的特征点。

公开(公告)号：US07835549B2

公开(公告)日：2010-11-16

申请号：US11368469

申请日：2006-03-07

申请人： Yoshiro Kitamura ,  Sadato Akahori ,  Kensuke Terakawa

发明人： Yoshiro Kitamura ,  Sadato Akahori ,  Kensuke Terakawa

IPC分类号： G06K9/00 ,  G06K9/62

CPC分类号： G06K9/00248 ,  G06K9/6256

摘要： A plurality of different facial images is used to cause a face classification apparatus to learn a characteristic feature of a face by using a machine-learning method. Each of the facial images includes a face which has the same direction and the same angle of inclination as those of a face included in each of the other facial images and each of the facial images is limited to an image of a specific facial region. For example, the facial region is a predetermined region including only a specific facial part other than a region below an upper lip to avoid an influence of a change in facial expressions. Alternatively, if the apparatus is used to detect a frontal face and to perform refined detection processing on the extracted face candidate, a region including only an eye or eyes, a nose and an upper lip is used as the facial region.

摘要翻译： 使用多种不同的面部图像来使面部分类装置通过使用机器学习方法来学习面部的特征。 每个面部图像包括具有与包括在每个其他面部图像中的面部相同的方向和相同的倾斜角度的面部，并且将每个面部图像限于特定面部区域的图像。 例如，面部区域是仅包括除了上唇下方的区域以外的特定面部部分的预定区域，以避免面部表情变化的影响。 或者，如果使用该装置检测正面，并对所提取的面部候选进行精细检测处理，则仅使用眼睛，眼睛，鼻子和上唇的区域用作面部区域。

公开(公告)号：US20120269443A1

公开(公告)日：2012-10-25

申请号：US13534817

申请日：2012-06-27

申请人： Yuanzhong LI ,  Sadato Akahori ,  Kensuke Terakawa ,  Yoshiro Kitamura ,  Wataru Ito

发明人： Yuanzhong LI ,  Sadato Akahori ,  Kensuke Terakawa ,  Yoshiro Kitamura ,  Wataru Ito

IPC分类号： G06K9/46

CPC分类号： G06K9/00281

摘要： First, a face within an image, which is a target of detection, is detected. Detection data of the face is employed to detect eyes which are included in the face. Detection data of the eyes are employed to detect the inner and outer corners of the eyes. Detection data of the inner and outer corners of the eyes is employed to detect characteristic points of the upper and lower eyelids that represent the outline of the eyes.

摘要翻译： 首先，检测作为检测对象的图像内的面部。 使用脸部的检测数据来检测包含在脸部中的眼睛。 眼睛的检测数据用于检测眼睛的内角和外角。 使用眼睛内外角的检测数据来检测表示眼睛轮廓的上眼睑和下眼睑的特征点。

公开(公告)号：US07801337B2

公开(公告)日：2010-09-21

申请号：US11652512

申请日：2007-01-12

申请人： Sadato Akahori ,  Kensuke Terakawa

发明人： Sadato Akahori ,  Kensuke Terakawa

IPC分类号： G06K9/00

CPC分类号： G06K9/00281 ,  G06K9/6215 ,  G06K9/6257 ,  G06K9/629

摘要： To detect a face image in an inputted image, predetermined-size partial images are cut out at different positions in the inputted image. An indicator value indicating a probability of each partial image being the face image is calculated. The partial images having the indicator values not less than a first threshold are extracted as candidate face images. Each candidate is set as a candidate of interest. If any nearby candidate is present within a predetermined coordinate distance from the candidate of interest, the candidate of interest and the nearby candidate are set in one candidate group. For each candidate group, an integrated indicator value reflecting the indicator values calculated for the candidates forming the candidate group is calculated. Then, an image within a predetermined area in the inputted image containing the candidate group having the integrated indicator value not less than a second threshold is extracted as the face image.

摘要翻译： 为了检测输入图像中的面部图像，在输入图像中的不同位置切出预定尺寸的部分图像。 计算指示每个部分图像是面部图像的概率的指示符值。 提取具有不小于第一阈值的指标值的部分图像作为候选面部图像。 每个候选人被设定为感兴趣的候选人。 如果任何附近的候选人存在于距感兴趣候选人的预定坐标距离内，则将感兴趣的候选人和附近的候选人设置在一个候选组中。 对于每个候选组，计算反映针对形成候选组的候选计算出的指标值的综合指标值。 然后，提取包含具有不小于第二阈值的积分指标值的候选组的输入图像内的预定区域内的图像作为面部图像。

公开(公告)号：US20060222217A1

公开(公告)日：2006-10-05

申请号：US11393708

申请日：2006-03-31

申请人： Yoshiro Kitamura ,  Sadato Akahori ,  Kensuke Terakawa

发明人： Yoshiro Kitamura ,  Sadato Akahori ,  Kensuke Terakawa

IPC分类号： G06K9/00 ,  G06K9/62

CPC分类号： G06K9/6256 ,  G06K9/00248

摘要： A face discrimnating process judges whether a discrimination target image is an image of a face, based on characteristic amounts of the discrimination target image. A first and a second brightness gradation converting process are administered as preliminary processes. The first brightness gradation converting process is administered on regions in which the degrees of variance of pixel values are greater than or equal to a first predetermined level. The second brightness gradation converting process is administered on regions in which the degrees of variance are less than the first predetermined level. The first brightness gradation converting process causes the degree of variance to approach a second predetermined level. The second brightness gradation converting process suppresses the degree of variance to be less than the second predetermined level.

摘要翻译： 面部鉴别处理基于鉴别目标图像的特征量判断辨别目标图像是否是脸部的图像。 第一和第二亮度灰度转换处理作为初步处理。 在像素值的方差大于或等于第一预定水平的区域上施加第一亮度灰度转换处理。 在方差小于第一预定水平的区域上施加第二亮度灰度转换处理。 第一亮度灰度转换处理使得方差程度接近第二预定水平。 第二亮度灰度转换处理将方差程度抑制成小于第二预定水平。

公开(公告)号：US20070189609A1

公开(公告)日：2007-08-16

申请号：US11393680

申请日：2006-03-31

申请人： Wataru Ito ,  Sadato Akahori ,  Kensuke Terakawa ,  Yoshiro Kitamura

发明人： Wataru Ito ,  Sadato Akahori ,  Kensuke Terakawa ,  Yoshiro Kitamura

IPC分类号： G06K9/62 ,  G06K9/46

CPC分类号： G06K9/00281 ,  G06K9/38 ,  G06K9/6292

摘要： A face discriminating process judges whether a discrimination target image is an image of a face, based on characteristic amounts of the discrimination target image. Gradation conversion of pixel values is administered as a preliminary process, to suppress fluctuations in contrast within the discrimination target image. In the gradation conversion process, degrees of variance of pixel values within local regions of the discrimination target image are caused to approach a predetermined level. The local regions are set to be of a size that includes a single eye of a face to be discriminated.

摘要翻译： 面部鉴别处理基于鉴别目标图像的特征量来判断辨别目标图像是否是脸部的图像。 作为初步处理来施加像素值的灰度变换，以抑制辨别目标图像内的对比度的波动。 在灰度转换处理中，鉴别目标图像的局部区域内的像素值的变化程度达到预定水平。 局部区域被设置为包括要被区别的脸的单个眼睛的尺寸。

公开(公告)号：US20070165951A1

公开(公告)日：2007-07-19

申请号：US11652512

申请日：2007-01-12

申请人： Sadato Akahori ,  Kensuke Terakawa

发明人： Sadato Akahori ,  Kensuke Terakawa

IPC分类号： G06K9/46

CPC分类号： G06K9/00281 ,  G06K9/6215 ,  G06K9/6257 ,  G06K9/629

摘要： To detect a face image in an inputted image, predetermined-size partial images are cut out at different positions in the inputted image. An indicator value indicating a probability of each partial image being the face image is calculated. The partial images having the indicator values not less than a first threshold are extracted as candidate face images. Each candidate is set as a candidate of interest. If any nearby candidate is present within a predetermined coordinate distance from the candidate of interest, the candidate of interest and the nearby candidate are set in one candidate group. For each candidate group, an integrated indicator value reflecting the indicator values calculated for the candidates forming the candidate group is calculated. Then, an image within a predetermined area in the inputted image containing the candidate group having the integrated indicator value not less than a second threshold is extracted as the face image.

摘要翻译： 为了检测输入图像中的面部图像，在输入图像中的不同位置切出预定尺寸的部分图像。 计算指示每个部分图像是面部图像的概率的指示符值。 提取具有不小于第一阈值的指标值的部分图像作为候选面部图像。 每个候选人被设定为感兴趣的候选人。 如果任何附近的候选人存在于距感兴趣候选人的预定坐标距离内，则将感兴趣的候选人和附近的候选人设置在一个候选组中。 对于每个候选组，计算反映针对形成候选组的候选计算出的指标值的综合指标值。 然后，提取包含具有不小于第二阈值的积分指标值的候选组的输入图像内的预定区域内的图像作为面部图像。